Search

JP-2026075471-A - Pipe replacement timing estimation system

JP2026075471AJP 2026075471 AJP2026075471 AJP 2026075471AJP-2026075471-A

Abstract

[Problem] To be able to estimate the timing for replacing pipes buried underground. [Solution] The estimation system (1) includes: an actual elapsed time acquisition unit (120) that acquires the actual elapsed time since the piping was buried; a repair history acquisition unit (140) that acquires the actual number of times the piping has been repaired; a repair timing estimation unit (150) that estimates the timing when the piping will be repaired in the near future by inputting the actual elapsed time or virtual elapsed time as input elapsed time and the actual number or an input number increased by 1 as a new input repair number to a machine learning model (160); a virtual elapsed time acquisition unit (170) that acquires the virtual elapsed time since the piping was buried when the most recent repair of the piping is to be performed based on the estimated timing; and a replacement timing calculation unit (180) that calculates the timing for replacing the piping based on the acquired virtual elapsed time when the input repair number reaches a given number. [Selection Diagram] Figure 3

Inventors

  • 井上 千鶴
  • 中村 郁仁
  • 田口 直斗
  • 井原 正晶
  • 野村 孟

Assignees

  • インフロニア・ホールディングス株式会社
  • Ｆｒａｃｔａ Ｊａｐａｎ株式会社

Dates

Publication Date
20260508
Application Date
20241022

Claims (8)

  1. A means for acquiring the actual elapsed time since the time of installation of pipes buried underground, A means for acquiring the number of repairs, which acquires the actual number of times the aforementioned piping has been repaired, A repair timing estimation means estimates the timing when repairs to the piping will be needed in the near future by inputting the actual elapsed time as the input elapsed time and the actual number of repairs as the input number of repairs to a trained machine learning model. A pipe replacement timing estimation system including a virtual elapsed time acquisition means that acquires a virtual elapsed time from the time the pipe was buried when the most recent repair of the pipe is to be performed, based on the timing estimated by the repair timing estimation means, The repair timing estimation means inputs the virtual elapsed time as the input elapsed time into the trained machine learning model, and also inputs the input number of repairs increased by 1 into the trained machine learning model, thereby estimating the next timing when further repairs to the piping will be necessary. The pipe replacement timing estimation system includes a replacement timing calculation means that repeatedly operates the repair timing estimation means and the virtual elapsed time acquisition means, and when the number of input repairs reaches a given number, calculates the timing of pipe replacement based on the virtual elapsed time acquired by the virtual elapsed time acquisition means.
  2. In the pipe replacement timing estimation system according to claim 1, The system further includes environmental information acquisition means for acquiring environmental information indicating the surrounding environment at the location where the aforementioned pipes are buried, The repair timing estimation means estimates the timing at which repairs to the piping will be necessary by inputting the input elapsed time, the number of input repairs, and the environmental information into the trained machine learning model. This is a pipe replacement timing estimation system.
  3. In the pipe replacement timing estimation system according to claim 1, The trained machine learning model is a model trained based on training data including the actual elapsed time, the actual number of times, and the timing at which the piping was actually repaired. This is a piping replacement timing estimation system.
  4. In the pipe replacement timing estimation system according to claim 2, The trained machine learning model is a model trained based on training data including the actual elapsed time, the actual number of times, the environmental information, and the timing when the piping was actually repaired. This is a piping replacement timing estimation system.
  5. In the pipe replacement timing estimation system according to claim 3 or 4, A pipe replacement timing estimation system, wherein the learning data is generated as learning data including a first timing when the pipe was actually repaired, based on the repair history of the pipe, and as learning data including a second timing when the pipe was actually repaired after the first timing.
  6. A means for acquiring the actual elapsed time since the time of installation of pipes buried underground, A means for acquiring the number of repairs, which acquires the actual number of times the aforementioned piping has been repaired, A repair timing estimation means estimates the timing when repairs to the piping will be needed in the near future by inputting the actual elapsed time as the input elapsed time and the actual number of repairs as the input number of repairs to a trained machine learning model. A pipe replacement timing estimation device, comprising: a virtual elapsed time acquisition means for acquiring a virtual elapsed time from the time the pipe was buried when the most recent repair of the pipe is to be performed, based on the timing estimated by the repair timing estimation means, The repair timing estimation means inputs the virtual elapsed time as the input elapsed time into the trained machine learning model, and also inputs the input number of repairs increased by 1 into the trained machine learning model, thereby estimating the next timing when further repairs to the piping will be necessary. The pipe replacement timing estimation device includes a replacement timing calculation means that repeatedly operates the repair timing estimation means and the virtual elapsed time acquisition means, and when the number of virtual repairs reaches a given number, calculates the timing of pipe replacement based on the virtual elapsed time acquired by the virtual elapsed time acquisition means.
  7. The means for acquiring actual elapsed time includes an actual elapsed time acquisition step for pipes buried underground, which acquires the actual elapsed time from the time of burial, The means for obtaining the number of repairs includes a step for obtaining the number of repairs, which obtains the actual number of times the piping has been repaired, A first repair timing estimation step involves the repair timing estimation means inputting the actual elapsed time as the input elapsed time and the actual number of repairs as the input number of repairs into a trained machine learning model to estimate the timing at which the piping will be repaired in the near future. The virtual elapsed time acquisition means acquires a virtual elapsed time from the time the pipe was buried when the most recent repair of the pipe is to be performed, based on the timing estimated by the repair timing estimation means, in a virtual elapsed time acquisition step. The repair timing estimation means inputs the virtual elapsed time as the input elapsed time into the trained machine learning model, and inputs the input number of repairs increased by 1 into the trained machine learning model, thereby estimating the next timing when further repairs to the piping will be necessary. The repair timing estimation means and the virtual elapsed time acquisition means perform the second repair timing estimation step and the virtual elapsed time acquisition step repeatedly, A pipe replacement timing estimation method, which includes a replacement timing calculation step in which, when the number of virtual repairs reaches a given number, the replacement timing calculation means calculates the replacement timing of the pipe based on the virtual elapsed time obtained by the virtual elapsed time acquisition step.
  8. Procedure for obtaining the actual elapsed time since the installation of pipes buried underground. A procedure for obtaining the number of repairs, which obtains the actual number of times the aforementioned piping has been repaired. A repair timing estimation procedure that estimates the timing when repairs to the piping will be needed in the near future by inputting the actual elapsed time as the input elapsed time and the actual number of repairs as the input number of repairs to a trained machine learning model, and A program that causes a computer to execute a virtual elapsed time acquisition procedure to acquire a virtual elapsed time from the time the pipe was buried when the most recent repair of the pipe is to be performed, based on the timing estimated by the repair timing estimation means, The repair timing estimation procedure involves inputting the virtual elapsed time as the input elapsed time into the trained machine learning model, and inputting the input number of repairs increased by 1 into the trained machine learning model, thereby estimating the next timing when further repairs to the piping will be necessary. The program causes the computer to repeatedly execute the repair timing estimation procedure and the virtual elapsed time acquisition procedure. The program is a program that causes the computer to execute a replacement timing calculation procedure, which calculates the timing for replacing the piping based on the virtual elapsed time obtained by the virtual elapsed time acquisition procedure, when the number of virtual repairs reaches a given number.

Description

This disclosure relates to a system for estimating the timing of pipe replacement. One method for evaluating the degree of deterioration of underground pipes is to judge it based on the time elapsed since burial (the year the pipes were laid) or the statutory useful life. Non-patent document 1 below describes calculating an evaluation value indicating the soundness of the pipes using a given formula, based on a numerical value indicating the elapsed time since the statutory useful life and numerical values indicating seismic resistance and water quality obtained from pipe inspections. Furthermore, the probability of needing repairs within a predetermined period (for example, within 5 years) is being predicted based on the elapsed time since burial, the material and diameter of the pipes, and the geological conditions of the burial location. "Guidelines on Asset Management in Water Supply Businesses, Part II: Specific Topics - Practical Methods of Asset Management," [online], Water Management and Land Conservation Bureau, Water Supply Business Division, Ministry of Land, Infrastructure, Transport and Tourism, [Accessed August 30, 2024], Internet <URL: https://www.mlit.go.jp/common/830000856.pdf> This diagram shows the configuration of the pipe replacement timing estimation system.This is a diagram showing an example of piping information.This figure shows an example of environmental information.This is a diagram showing an example of a repair history.This is a functional block diagram showing an example of the functions implemented in the pipe replacement timing estimation system.This is a diagram showing an example of an area where pipes are buried.This figure shows an example of the input data entered into the machine learning model during the initial estimation, the repair timing output from the machine learning model, and the calculated hypothetical elapsed time.This figure shows an example of the input data to be fed into the machine learning model for the next estimation, the repair timing output by the machine learning model, and the calculated hypothetical elapsed time.This figure shows an example of a method for generating training data used to train machine learning models.This is a flowchart illustrating the flow of the estimation process performed by the pipe replacement timing estimation system. The following describes the pipe replacement timing estimation system 1 proposed in this disclosure (hereinafter simply referred to as estimation system 1), with reference to the drawings. As described below, estimation system 1 is designed to estimate the replacement timing of pipes buried underground. [1. Hardware Configuration] Figure 1 shows the hardware configuration of the estimation system 1. As shown in Figure 1, the estimation system 1 may include a pipe replacement timing estimation device 10 (hereinafter simply referred to as the estimation device 10), a pipe information storage device 20, an environmental information storage device 30, and a repair history storage device 40. The estimation device 10 may be a computer such as a desktop personal computer, a server device, a mobile terminal (e.g., a tablet device or smartphone), or a general-purpose computer. The pipe information storage device 20, the environmental information storage device 30, and the repair history storage device 40 may be computers such as server devices different from the estimation device 10, or they may be storage devices such as NAS (Network Attached Storage), solid-state drives, or hard disk drives. The estimation device 10, piping information storage device 20, environmental information storage device 30, and repair history storage device 40 may be connected to each other via a network such as a LAN (Local Area Network). Furthermore, these devices may be located at geographically separated locations (for example, different business offices). In this case, these devices may be connected to each other via a network such as the Internet. As shown in Figure 1, the estimation device 10 may include a processor 11, a storage unit 12, a communication unit 13, a display unit 14, and an operation unit 15. The estimation device 10 may also include an optical disc drive for reading optical discs and data input/output terminals such as a USB (Universal Serial Bus) port. The processor 11 may be a program control device such as a CPU (Central Processing Unit). The storage unit 12 may be a memory element such as ROM (Read Only Memory) or RAM (Random Access Memory), a solid-state drive, or a hard disk drive. The storage unit 12 of the estimation device 10 may store data such as programs executed by the processor 11. The communication unit 13 may be a communication interface such as a network board. The communication unit 13 may be capable of wired or wireless communication with other devices (for example, storage devices such as a piping information storage device 20, an environmental information storage device 30, and a repair histor